youtube_dl/extractor/youporn.py

   1 import json
   2 import os
   3 import re
   4 import sys
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10
  11     ExtractorError,
  12     unescapeHTML,
  13     unified_strdate,
  14 )
  15 from ..aes import (
  16     aes_decrypt_text
  17 )
  18
  19 class YouPornIE(InfoExtractor):
  20     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
  21     _TEST = {
  22         u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  23         u'file': u'505835.mp4',
  24         u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
  25         u'info_dict': {
  26             u"upload_date": u"20101221",
  27             u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
  28             u"uploader": u"Ask Dan And Jennifer",
  29             u"title": u"Sex Ed: Is It Safe To Masturbate Daily?",
  30             u"age_limit": 18,
  31         }
  32     }
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36         video_id = mobj.group('videoid')
  37
  38         req = compat_urllib_request.Request(url)
  39         req.add_header('Cookie', 'age_verified=1')
  40         webpage = self._download_webpage(req, video_id)
  41         age_limit = self._rta_search(webpage)
  42
  43         # Get JSON parameters
  44         json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
  45         try:
  46             params = json.loads(json_params)
  47         except:
  48             raise ExtractorError(u'Invalid JSON')
  49
  50         self.report_extraction(video_id)
  51         try:
  52             video_title = params['title']
  53             upload_date = unified_strdate(params['release_date_f'])
  54             video_description = params['description']
  55             video_uploader = params['submitted_by']
  56             thumbnail = params['thumbnails'][0]['image']
  57         except KeyError:
  58             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
  59
  60         # Get all of the links from the page
  61         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
  62         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
  63             webpage, u'download list').strip()
  64         LINK_RE = r'<a href="([^"]+)">'
  65         links = re.findall(LINK_RE, download_list_html)
  66
  67         # Get all encrypted links
  68         encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
  69         for encrypted_link in encrypted_links:
  70             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
  71             links.append(link)
  72
  73         if not links:
  74             raise ExtractorError(u'ERROR: no known formats available for video')
  75
  76         formats = []
  77         for link in links:
  78
  79             # A link looks like this:
  80             # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
  81             # A path looks like this:
  82             # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
  83             video_url = unescapeHTML( link )
  84             path = compat_urllib_parse_urlparse( video_url ).path
  85             extension = os.path.splitext( path )[1][1:]
  86             format = path.split('/')[4].split('_')[:2]
  87
  88             # size = format[0]
  89             # bitrate = format[1]
  90             format = "-".join( format )
  91             # title = u'%s-%s-%s' % (video_title, size, bitrate)
  92
  93             formats.append({
  94                 'url': video_url,
  95                 'ext': extension,
  96                 'format': format,
  97                 'format_id': format,
  98             })
  99
 100         # Sort and remove doubles
 101         formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
 102         for i in range(len(formats)-1,0,-1):
 103             if formats[i]['format_id'] == formats[i-1]['format_id']:
 104                 del formats[i]
 105
 106         return {
 107             'id': video_id,
 108             'uploader': video_uploader,
 109             'upload_date': upload_date,
 110             'title': video_title,
 111             'thumbnail': thumbnail,
 112             'description': video_description,
 113             'age_limit': age_limit,
 114             'formats': formats,
 115         }